Being first to the terabyte mark gives Hitachi bragging rights, and more importantly, the ability to offer single-drive storage capacity 33% greater than that of its competitors. Hitachi isn’t banking on capacity alone, though. The 7K1000 is also outfitted with a whopping 32MB of cachedouble what you get with other 3.5″ hard drives. Couple that extra cache with 200GB platters that have the highest areal density of any drive on the market, and the 7K1000’s performance could impress as much as its capacity.
Has Hitachi achieved a perfect balance of speed and storage with its Deskstar 7K1000? We’ve tested it against nearly 20 competitorsincluding its closest 750GB rivals from Seagate and Western Digitalto find out.
When a terabyte isn’t
By now I’ve no doubt been heckled by someone insisting that the 7K1000 doesn’t actually offer a full terabyte of storage capacity. This person probably sounds like the comic book guy from The Simpsons, but don’t dismiss him. He has a point, sort of.
According to the International System of Units (SI), a terabyte consists of 1,000,000,000,000 bytes10004, or 1012. Windows confirms that the 7K1000 delivers 1,000,202,240,000 bytes, which is more than it needs, so what’s the comic book guy on about?
Look a little closer, and you’ll see that while the 7K1000 does indeed offer over a trillion bytes, that capacity only translates to 931 gigabytes. For an explanation of why, we have to delve into the always exciting world of numerical systems. SI units are built on the same base 10 decimal system we’ve been using since grade school. Computers, however, use a binary base 2 system. So, while a kilobyte in decimal is 1,000 bytes, a kilobyte in binary translates to 1,024 bytes. A binary terabyte, then, is not 1,0004, but 1,0244, or 240.
Multiplying that out, a binary terabyte yields 1,099,511,627,776 bytes, which is why the 7K1000 falls short of a thousand gigabytes. The drive would actually need 1,024 gigabytes to achieve terabyte status in the binary world. This translation problem isn’t unique to the 7K1000, either. Virtually all hard drives advertise their capacities in SI units, so their actual capacities fall short of binary expectations.
Back in the day, the gap between decimal and binary capacity wasn’t big enough to ruffle feathers. Gigabyte drives were only “missing” 24 megabytes, and that was easy to swallow. However, higher capacities widen the disconnect between decimal and binary, leading the terabyte 7K1000 to pull up 69GB short. If you take out multimedia files, 69GB is probably more than enough capacity for what most of us have on our hard drives, so it’s hardly a drop in the bucket.
To help ease the confusion surrounding the PC’s base 2 binary system, various standards bodies are pushing a set of alternative binary prefixes. A terabyte would remain one trillion bytes, while “tebibyte” would denote 1,099,511,627,776 bytes. Needless to say, that hasn’t caught on yet. However, as growing hard drive capacities increase the amount of space “lost” in binary to decimal conversion, the tebibyte’s time may come.
Now that we have the math sorted out, it’s time to take a look at the Deskstar. Not that there’s much to see.
The 7K1000 looks like just about any other desktop drive. Only a couple of characters on the label serve as evidence of its monstrous capacity. Hard drives don’t need to score high on artistic impression, of course, but I’m continually surprised to see manufacturers wrapping their flagship products in the same generic skin as budget models. You’d think the reigning capacity king would have a little more flair, but there’s nothing to visually set the 7K1000 apart from other Deskstar models or even competitor drives.
|Maximum external transfer rate||300MB/s|
|Buffer to disk transfer rate||1070Mbps|
|Read seek time||8.5ms|
|Write seek time||9.2ms|
|Average rotational latency||4.17ms|
|Available capacities||750GB, 1TB|
|Idle acoustics||2.9 bels|
|Seek acoustics||3.0-3.2 bels|
|Idle power consumption||8.1-9.0W|
|Read/write power consumption||12.8-13.6W|
|Native Command Queuing||Yes|
|Warranty length||Three years|
To see what makes the 7K1000 special, you have to dig into the drive’s spec sheet. Terabyte capacity is obviously what makes this drive unique, but how it gets there is also important. The 7K1000 uses five platters to achieve its industry-leading capacity, perpendicularly packing an impressive 200GB onto each disk. These 200GB platters give the 7K1000 a higher areal density than competing drives that typically feature 188GB platters, and since higher areal densities can lead to better performance by allowing the drive head to access more data across the same physical area, the Deskstar is nicely set up for speed.
Copious amounts of cache should also help the 7K1000 in the performance department. Serial ATA hard drives typically come with either 8MB or 16MB of onboard cache, but the Deskstar packs a whopping 32MB thanks to a single Hynix memory chip. Hitachi didn’t add capacity to the Deskstar by turning the drive into a clumsy minivan, then; they built the hard drive equivalent of an Audi RS4 Avant.
With the 7K1000 breaking new ground in cache size and capacity, it’s almost amusing to see the drive hanging onto an old-school molex power connector. Power plug flexibility isn’t a problem, of course, and it may actually come in handy for those looking to deploy the drive in extremely large storage arrays, since power supplies typically only come with a handful of SATA power connectors.
A RAID array might be a good idea if you actually have a terabyte’s worth of data you’d like to store on the 7K1000. That’s a lot to lose, and despite the fact that Hitachi covers the drive with a three-year warranty, that warranty will only get you a replacement drive if yours failsit won’t restore your data.
Before diving into testing, we should take a moment to give the folks at NCIX a shout out for hooking up with the 7K1000 we used for testing. We’ve been dealing with NCIX for a long time, and you can now sample their wares stateside at NCIXUS.
We’ll be comparing the performance of the Deskstar 7K1000 1TB with that of a slew of competitors, including some of the latest and greatest Serial ATA drives from Hitachi, Maxtor, Samsung, Seagate, and Western Digital. These drives differ when it comes to external transfer rates, spindle speeds, cache sizes, platter densities, NCQ support, and capacity, all of which can have an impact on performance. Keep in mind the following differences as we move through our benchmarks:
|Max external transfer rate||Spindle speed||Cache size||Platter size||Capacity||Native Command Queuing?|
|Barracuda 7200.7 NCQ||150MB/s||7,200RPM||8MB||80GB||160GB||Yes|
|Barracuda 7200.9 (160GB)||300MB/s||7,200RPM||8MB||160GB||160GB||Yes|
|Barracuda 7200.9 (500GB)||300MB/s||7,200RPM||16MB||125GB||500GB||Yes|
|Caviar SE16 (500GB)||300MB/s||7,200RPM||16MB||125GB||500GB||Yes|
|Caviar SE16 (750GB)||300MB/s||7,200RPM||16MB||188GB||750GB||Yes|
|Caviar RE2 (500GB)||300MB/s||7,200RPM||16MB||125GB||500GB||Yes|
Note that the 250GB Caviar SE16 and the Raptor WD740GD lack support for Native Command Queuing. The WD740GD does support a form of command queuing known as Tagged Command Queuing (TCQ), but host controller and chipset support for TCQ is pretty thin. Our Intel 955X-based test platform doesn’t support TCQ.
We have test results from several versions of Western Digital’s Caviar SE16 and RE2. To avoid confusion, we’ll be listing their capacities in parentheses in each of our graphs.
Since Seagate makes versions of the 7200.7 both with and without NCQ support, the 7200.7 in our tests appears as the “Barracuda 7200.7 NCQ” to clarify that it’s the NCQ version of the drive. The other drives aren’t explicitly labeled as NCQ drives because they’re not available without NCQ support.
Finally, we should note that our WD1500ADFD has a slightly newer firmware revision than the Raptor X sample we’ve had since February, 2006. The drives still share identical internals, but firmware optimizations could give our newer Raptor an edge over the X in some tests.
Performance data from such a daunting collection of drives can make our graphs a little hard to read, so I’ve highlighted the 7K1000 in bright yellow and its high-capacity competitorsthe Barracuda 7200.10 and ES, and the Caviar SE16 750GBin pale yellow to set them apart from the others. We also have two sets of IOMeter graphs: one with all the drives, and another with just the Deskstar and its 750GB rivals. Most of our analysis will be limited to how the 7K1000 compares with its direct rivals, so it should be easy to follow along.
Our testing methods
All tests were run three times, and their results were averaged, using the following test system.
We used the following versions of our test applications:
- WorldBench 5.0
- Intel IOMeter v2004.07.30
- Xbit Labs File Copy Test v1.0 beta 13
- TCD Labs HD Tach v3.01
- Far Cry v1.3
- DOOM 3
- Intel iPEAK Storage Performance Toolkit 3.0
The test systems’ Windows desktop was set at 1280×1024 in 32-bit color at an 85Hz screen refresh rate. Vertical refresh sync (vsync) was disabled for all tests.
All the tests and methods we employed are publicly available and reproducible. If you have questions about our methods, hit our forums to talk with us about them.
WorldBench uses scripting to step through a series of tasks in common Windows applications. It then produces an overall score. WorldBench also spits out individual results for its component application tests, allowing us to compare performance in each. We’ll look at the overall score, and then we’ll show individual application results.
The Deskstar doesn’t quite manage to top the field in WorldBench, but it’s only one point off the lead. Note that the drive’s closest competitors are all within a point of the 7K1000, as well.
Multimedia editing and encoding
Windows Media Encoder
VideoWave Movie Creator
Premiere is the only one of WorldBench’s multimedia editing and encoding tests to tax the storage subsystem, and again, the Deskstar finds itself a little off the lead. The 7K1000 is seven seconds slower than Western Digital’s 750GB Caviar SE16 in this test, but that still makes it the second fastest 7,200-RPM drive.
Photoshop is a wash, but ACDSee manages to spread the field a little. There, the Deskstar again finds itself sitting between Western Digital and Seagate’s 750GB drives, with the former taking the lead once again.
Multitasking and office applications
Mozilla and Windows Media Encoder
There isn’t much to see in WorldBench’s multitasking and office application tests. The 7K1000 does take top honors with the suite’s Office XP and Mozilla media encode workloads, but it doesn’t really distance itself from the other drives.
WinZip and Nero give the Deskstar a chance to really stretch its legs. Unfortunately, those legs are a little short, as the 7K1000 finds itself behind not only the 750GB Caviar, but also Seagate’s Barracuda ES and 7200.10.
To test system boot and game level load times, we busted out our trusty stopwatch.
Our system boot time test proves disastrous for the Deskstar. The drive is nearly six seconds slower than its closest competitor and more than 20 seconds slower than its Caviar-based competition.
Things improve for Hitachi when we move to game load times, where the Deskstar manages to trump its 750GB rivals.
File Copy Test is a pseudo-real-world benchmark that times how long it takes to create, read, and copy files in various test patterns. File copying is tested twice: once with the source and target on the same partition, and once with the target on a separate partition. Scores are presented in MB/s.
To make things easier to read, we’ve busted out our FC-Test results into individual graphs for each test pattern. We’ll tackle file creation performance first.
With the highest areal density of the lot and a beefy 32MB cache, the Deskstar should have the edge here. Except it doesn’t. At best, the drive manages a third-place performance behind the 750GB Caviar SE16 with the Install test pattern, but it lags farther behind with other test patterns. At least the 7K1000 is consistently faster than the Barracuda ES and 7200.10.
Now that we’ve created the files dictated by all these test patterns, let’s see how fast the drives can read them.
Finally, the 7K1000 starts to flex its muscles. The drive manages to top the field with the Windows and Programs test patterns, which feature a large number of small files, and it’s not far off the lead with the others. To be fair, though, the Deskstar’s wins come by the slimmest of margins; the 750GB Caviar SE16 is the fastest high-capacity drive overall.
Next, File Copy Test combines read and write tasks with some, er, copy tests.
Results are mixed here, with the Deskstar jumping from a pack-leading performance with the Windows test pattern to dragging its feet behind even the 750GB ‘cudas with the ISO and MP3 test patterns. The 7K1000 appears to favor test patterns with larger numbers of small files, which is why it does reasonably well with the Install and Programs test patterns.
FC-Test’s second wave of copy tests involves copying files from one partition to another on the same drive.
The Deskstar struggles with this batch of partition copy tests, finding itself behind its closest rivals in three of four test patternsand by a large margin in two of those tests. Things look better with the Programs and Windows test patterns, but even then, the Deskstar still trails the 750GB Caviar SE16.
We’ve developed a series of disk-intensive multitasking tests to highlight the impact of command queuing on hard drive performance. You can get the low-down on these iPEAK-based tests here. The mean service time of each drive is reported in milliseconds, with lower values representing better performance.
The Deskstar exacts revenge on the Caviar SE16 in our first batch of iPEAK tests, managing to trump all takers with two of five test patterns. The Barracudas aren’t even close in these tests. Although the Caviar fares better with compressed file extraction, the Deskstar is faster at compressed file creation.
Our second batch of iPEAK workloads finds the Deskstar holding its own rather nicely. The drive blazes to victory in workloads that combine Outlook import and export tasks with file copy operations, easily beating its high-capacity competitors. Western Digital’s 750GB Caviar does nose ahead when we combine an Outlook export with a VirtualDub import, but it’s well behind when that Outlook export becomes an import.
IOMeter presents a good test case for command queuing, so the NCQ-less Western Digital Caviar SE16 250GB and Raptor WD740GD should have a slight disadvantage here under higher loads. To keep things easy to read, we’ve busted out two sets of graphs here. The first includes the Deskstar 7K1000 and its closest competitors, while the second has results for all the drives we’ve tested. With close to 20 drives, those latter graphs are a little difficult to read, so we’ll focus our attention on the first set and the Deskstar’s direct rivals.
The 7K1000’s IOMeter transaction rates are interesting to say the least. With lower numbers of concurrent I/O requests, the drive’s throughput places it at the back of the class. However, when we crank up to higher I/O levels, the Deskstar’s throughput ramps more aggressively, as if we’d just woken the drive up. So, the Deskstar is the slowest drive up to between 32 and 64 outstanding I/O requests, but it’s actually the fastestor nearly therewhen we peak at 256 I/O requests.
Good luck with these, folks.
Turning our attention to IOMeter response times, we see a similar patter emerge. The Deskstar trails its rivals with fewer I/O requests, but seems to warm up and surge into contention as the load approaches a peak of 256 outstanding I/Os. Of course, you’ll need a busy multi-user environment to slam a drive with that many concurrent I/O requests; typical desktop workloads don’t even come close.
CPU utilization is below half a percent for all four drives.
We tested HD Tach with the benchmark’s full variable zone size setting.
The Deskstar’s best-in-class areal density should give it an edge in HD Tach’s sustained read and write speed tests, but the drive only manages a fourth-place performance in each. To be fair, the 7K1000 does lose to a couple of 10K-RPM Raptors. However, even if you take those out of the equation, the 7,200RPM Caviar SE16 750GB is still faster by about 5MB/s.
Burst performance is a little disappointing on the Deskstar. The drive falls 16MB short of the Caviar SE16 here and more than 37MB/s short of the ‘cudas. The 7K1000’s 32MB cache may be capacious, but it doesn’t look that fast in this test.
At least the Deskstar’s access times are quick. In fact, they’re nearly the fastest of any 7,200-RPM drive we’ve tested and about a millisecond faster than the 7K1000’s direct rivals.
CPU utilization is within HD Tach’s +/- 2% margin of error in this test. Move along.
Noise levels were measured with an Extech 407727 Digital Sound Level meter 1″ from the side of the drives at idle and under an HD Tach seek load. Drives were run with the PCB facing up.
The Deskstar 7K1000 isn’t a loud drive by any means, but it’s not a particularly quiet one, either. This fact is especially apparent under seek loads, where the Deskstar is close to three decibels louder than the 750GB Caviar SE16. The Caviar is actually louder at idle, though, with the 750GB Barracudas claiming the lowest noise levels of any high-capacity drives at idle.
For our power consumption tests, we measured the voltage drop across a 0.1-ohm resistor placed in line with the 5V and 12V lines connected to each drive. Through the magic of Ohm’s Law, we were able to calculate the power draw from each voltage rail and add them together for the total power draw of the drive.
For a five-platter drive, the 7K1000’s power consumption is impressively low at idle. However, when you kick the drive into action, power draw almost doubles, pushing the Deskstar to the back of the pack. Note the nearly 5W gap between the 750GB Caviar SE16 and the 7K1000 under load.
Everyone remembers their first, be it a kiss, a car, or the clumsy back-seat combination of the two. As the first hard drive to reach the terabyte mark, Hitachi’s Deskstar 7K1000 will be remembered, too. Squeezing a trillion bytes into a 3.5″ hard drive form factor is a monumental engineering achievementone that rival hard drive manufacturers have yet to replicate and bring to market. The question, of course, is whether the 7K1000 has value beyond its unique status as the first terabyte drive you can buy.
I’m not so sure.
On the performance front, the Deskstar may be faster overall than Seagate’s 750GB Barracudas, but those drives are more than a year old. Against Western Digital’s latest 750GB Caviar SE16, the Deskstar most often finds itself trailing. That’s a disappointing result considering the 7K1000’s higher areal density and massive 32MB cache. Frankly, we expected the drive to be faster.
Of course, the Deskstar’s rivals fall 250GB short on the capacity front. Their cost per gigabyte is also substantially lower, though. The 7K1000 sells for as low as $345, so you’re paying about $0.35 per gigabyte. Meanwhile, the 750GB Caviar SE16 can be had for as little as $189, which is only just a little over $0.25 per gigabyte.
One expects to pay a premium on the highest capacity drive in a given range, but $0.10/gigabyte is quite a gap to span for a drive that offers few performance highlights and unremarkable noise levels. You’re paying for the milestone, I guess, or the exclusivity that comes with being the only terabyte drive on the market. In the end, we’d only recommend the Deskstar 7K1000 if you absolutely must have terabyte of capacity in a single 3.5″ drive. It’s fitting, then, that the 7K1000’s defining feature turns out to be the best reason to buy it.